EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Spectrum-Driven Hierarchical Learning Network for Aero-Engine Defect Segmentation

Yining Xie, Aoqi Shen, Haochen Qi, Jing Zhao, Jianpeng Li, Xichun Pan, Anlong Zhang

Computation · 25.04.2026 · 14 (5) · 99

DOI: 10.3390/computation14050099 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computation, online erschienen am 25.04.2026. Verfasst von Yining Xie und 6 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Postdoctoral Science Foundation, Natural Science Foundation of Heilongjiang Province, Open Fund Project of the Ministry of Education Key Laboratory.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aero-engine defects often exhibit micro-scale and high-frequency characteristics under complex metallic textures, which makes precise segmentation difficult. Most existing pixel-level methods rely on spatial-domain modeling and lack frequency-domain decoupling. As a result, high-frequency details are easily hidden by low-frequency background information. In addition, repeated downsampling weakens the representation of fine-grained structures, leading to inaccurate boundary localization and limited robustness. To address these issues, a spectrum-driven hierarchical learning network is proposed for aero-engine defect segmentation. First, a dual-band spectral module is constructed using the discrete cosine transform to separate high-frequency and low-frequency components, providing stable and physically meaningful frequency-domain priors for the network. Second, a detail-guided module is designed where high-frequency features adaptively guide skip connections, compensating information loss during encoding and improving boundary recovery. Furthermore, a low-frequency-driven region-aware modeling module is developed. The internal defect regions, boundary areas, and background regions are modeled hierarchically. A dynamic hyper-kernel generation mechanism performs region-sensitive convolutional modeling, improving adaptation to complex structural variations. Extensive experiments on the Turbo19 and NEU-Seg datasets demonstrate that the proposed method produces accurate defect boundaries and achieves mIoU scores of 89.82% and 91.44%, improving over the second-best method by 5.22% and 4.42%, respectively.

Förderung

  • China Postdoctoral Science Foundation
  • Natural Science Foundation of Heilongjiang Province
  • Open Fund Project of the Ministry of Education Key Laboratory
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Xie, Y., Shen, A., Qi, H., Zhao, J., Li, J., Pan, X., & Zhang, A. (2026). A Spectrum-Driven Hierarchical Learning Network for Aero-Engine Defect Segmentation. Computation, 14(5), 99. https://doi.org/10.3390/computation14050099

Vancouver

Xie Y, Shen A, Qi H, Zhao J, Li J, Pan X, et al. A Spectrum-Driven Hierarchical Learning Network for Aero-Engine Defect Segmentation. Computation. 2026;14(5):99. doi:10.3390/computation14050099

BibTeX
@article{Xie2026,
  author = {Xie, Yining and Shen, Aoqi and Qi, Haochen and Zhao, Jing and Li, Jianpeng and Pan, Xichun and Zhang, Anlong},
  title = {A Spectrum-Driven Hierarchical Learning Network for Aero-Engine Defect Segmentation},
  journal = {Computation},
  year = {2026},
  volume = {14},
  number = {5},
  pages = {99},
  doi = {10.3390/computation14050099}
}
Kostenlos starten →